AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Any2Critical: Safety-Critical Scenario Generation from Arbitrary Real-World Driving Contexts

Yao Huang, Yubo Chen, Ruochen Zhang, Yitong Sun, Shouwei Ruan, Zhenyu Wu, Yinpeng Dong, Xingxing Wei

AAAI 2026 · Image generation › Autoregressive and latent generation · approach: Diffusion planning and policies · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add RAG retrieval from NHTSA-5K accident database (ablation)Any2Critical · all scenarioscollision rate: 0.79 -> 0.90Improved
add RAG retrieval from NHTSA-5K accident database (ablation)Any2Critical · all scenariosplausibility: 0.87 -> 0.95Improved
add rule-based plausibility validation (ablation)Any2Critical · all scenarioscollision rate: 0.81 -> 0.90Improved
add rule-based plausibility validation (ablation)Any2Critical · all scenariosplausibility: 0.88 -> 0.95Improved
add RAG retrieval from NHTSA-5K accident database (ablation)Any2Critical · all scenariosoverall score (lower is more critical): 0.23 -> 0.14Improved
use Any2Critical scenarios instead of ChatSceneIDM driving model · Generated scenarios vs IDMcollision rate: 0.76 -> 1.00Improved
use Any2Critical scenarios instead of FWCTD3 driving model · Generated scenarios vs TD3collision rate: 0.91 -> 0.92No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy